spring Ai框架整合Ollama，调用本地大模型

Ollama使用

Ollama是一个用于在本地计算机上运行大模型的软件
软件运行后监听11434端口，自己写的程序要调大模型就用这个端口

ollama命令
ollama list：显示模型列表
ollama show：显示模型的信息
ollama pull：拉取模型
ollama push：推送模型
ollama cp：拷贝一个模型
ollama rm：删除一个模型
ollama run：运行一个模型

ollama全是命令行下操作，所以结合web客户端界面使用【安装可选】
主流的web工具
1 Openwebui
2 LobeChat,功能强大，可调用Ollama的模型，也可调用openai,google的等，在设置界面中配置url和key即可

spring Ai框架调用

1 pom.xml，注意添加的依赖和配置了仓库

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>3.2.5</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>
    <groupId>com.example</groupId>
    <artifactId>spring-ai-ollama</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>spring-ai-ollama</name>
    <description>spring-ai-ollama</description>
    <properties>
        <java.version>17</java.version>
        <spring-ai.version>0.8.1</spring-ai.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>

        <dependency>
            <groupId>io.springboot.ai</groupId>
            <artifactId>spring-ai-ollama-spring-boot-starter</artifactId>
            <version>1.0.0</version>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-devtools</artifactId>
            <scope>runtime</scope>
            <optional>true</optional>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <optional>true</optional>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
    </dependencies>
    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>org.springframework.ai</groupId>
                <artifactId>spring-ai-bom</artifactId>
                <version>${spring-ai.version}</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>

    <build>
        <plugins>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
                <configuration>
                    <excludes>
                        <exclude>
                            <groupId>org.projectlombok</groupId>
                            <artifactId>lombok</artifactId>
                        </exclude>
                    </excludes>
                </configuration>
            </plugin>
        </plugins>
    </build>
    <repositories>
        <repository>
            <id>spring-milestones</id>
            <name>Spring Milestones</name>
            <url>https://repo.spring.io/milestone</url>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </repository>
    </repositories>

</project>

2 yml配置，写自己的 Ollama 地址，模型用哪个，先用Ollama去下载

spring:
  application:
    name: spring-ai-ollama

  ai:
    ollama:
      base-url: http://120.55.99.218:11434
      chat:
        options:
          model: gemma:7b

3 测试

import org.springframework.ai.chat.ChatResponse;
import org.springframework.ai.chat.messages.AssistantMessage;
import org.springframework.ai.chat.prompt.Prompt;
import org.springframework.ai.chat.prompt.PromptTemplate;
import org.springframework.ai.ollama.OllamaChatClient;
import org.springframework.ai.ollama.api.OllamaOptions;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.*;

@RestController
public class AiController {

    @Autowired
    private OllamaChatClient ollamaChatClient;

    @GetMapping(value = "/chat_1")
    public String chat_1(@RequestParam(value = "message") String message) {
        String call = ollamaChatClient.call(message);
        System.out.println("模型回答 = " + call);
        return call;
    }

    @GetMapping(value = "/chat_2")
    public Object chat_2(@RequestParam(value = "message") String message) {
        Prompt prompt = new Prompt(
                message,
                OllamaOptions.create()
                        //代码中配置，会覆盖application.yml中的配置
                        .withModel("gemma:7b") //使用什么大模型
                        .withTemperature(0.9F) //温度高，更发散,准确性降低，温度低，更保守，准确性高
        );

        ChatResponse call = ollamaChatClient.call(prompt);
        AssistantMessage output = call.getResult().getOutput();
        System.out.println("模型回答 = " + output.getContent());
        return output;
    }

    @GetMapping("/chat_3/{size}")
    public String chatYear(@PathVariable("size") Integer size) {
        String message = "随便写一句话,{size} 字以内";
        PromptTemplate promptTemplate = new PromptTemplate(message);
        promptTemplate.add("size", size);
        System.out.println(promptTemplate.render());
        return ollamaChatClient.call(promptTemplate.render());
    }
}